dmaengine: fsl-dpaa2-qdma: Add NXP dpaa2 qDMA controller driver for Layerscape SoCs

DPPA2(Data Path Acceleration Architecture 2) qDMA supports
virtualized channel by allowing DMA jobs to be enqueued into
different work queues. Core can initiate a DMA transaction by
preparing a frame descriptor(FD) for each DMA job and enqueuing
this job through a hardware portal. DPAA2 components can also
prepare a FD and enqueue a DMA job through a hardware portal.
The qDMA prefetches DMA jobs through DPAA2 hardware portal. It
then schedules and dispatches to internal DMA hardware engines,
which generate read and write requests. Both qDMA source data and
destination data can be either contiguous or non-contiguous using
one or more scatter/gather tables.
The qDMA supports global bandwidth flow control where all DMA
transactions are stalled if the bandwidth threshold has been reached.
Also supported are transaction based read throttling.

Add NXP dppa2 qDMA to support some of Layerscape SoCs.
such as: LS1088A, LS208xA, LX2, etc.
Signed-off-by: Peng Ma <peng.ma@nxp.com>
Link: https://lore.kernel.org/r/20190930020440.7754-2-peng.ma@nxp.comSigned-off-by: Vinod Koul <vkoul@kernel.org>

drivers/dma/Kconfig

@@ -669,6 +669,8 @@ source "drivers/dma/sh/Kconfig"
 
 source "drivers/dma/ti/Kconfig"
 
+source "drivers/dma/fsl-dpaa2-qdma/Kconfig"
+
 # clients
 comment "DMA Clients"
 	depends on DMA_ENGINE

drivers/dma/Makefile

@@ -75,6 +75,7 @@ obj-$(CONFIG_UNIPHIER_MDMAC) += uniphier-mdmac.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
 obj-$(CONFIG_ZX_DMA) += zx_dma.o
 obj-$(CONFIG_ST_FDMA) += st_fdma.o
+obj-$(CONFIG_FSL_DPAA2_QDMA) += fsl-dpaa2-qdma/
 
 obj-y += mediatek/
 obj-y += qcom/

drivers/dma/fsl-dpaa2-qdma/Kconfig

+menuconfig FSL_DPAA2_QDMA
+	tristate "NXP DPAA2 QDMA"
+	depends on ARM64
+	depends on FSL_MC_BUS && FSL_MC_DPIO
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  NXP Data Path Acceleration Architecture 2 QDMA driver,
+	  using the NXP MC bus driver.

drivers/dma/fsl-dpaa2-qdma/Makefile

+# SPDX-License-Identifier: GPL-2.0
+# Makefile for the NXP DPAA2 qDMA controllers
+obj-$(CONFIG_FSL_DPAA2_QDMA) += dpaa2-qdma.o dpdmai.o

drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright 2019 NXP */
+
+#ifndef __DPAA2_QDMA_H
+#define __DPAA2_QDMA_H
+
+#define DPAA2_QDMA_STORE_SIZE 16
+#define NUM_CH 8
+
+struct dpaa2_qdma_sd_d {
+	u32 rsv:32;
+	union {
+		struct {
+			u32 ssd:12; /* souce stride distance */
+			u32 sss:12; /* souce stride size */
+			u32 rsv1:8;
+		} sdf;
+		struct {
+			u32 dsd:12; /* Destination stride distance */
+			u32 dss:12; /* Destination stride size */
+			u32 rsv2:8;
+		} ddf;
+	} df;
+	u32 rbpcmd;	/* Route-by-port command */
+	u32 cmd;
+} __attribute__((__packed__));
+
+/* Source descriptor command read transaction type for RBP=0: */
+/* coherent copy of cacheable memory */
+#define QDMA_SD_CMD_RDTTYPE_COHERENT (0xb << 28)
+/* Destination descriptor command write transaction type for RBP=0: */
+/* coherent copy of cacheable memory */
+#define QDMA_DD_CMD_WRTTYPE_COHERENT (0x6 << 28)
+#define LX2160_QDMA_DD_CMD_WRTTYPE_COHERENT (0xb << 28)
+
+#define QMAN_FD_FMT_ENABLE	BIT(0) /* frame list table enable */
+#define QMAN_FD_BMT_ENABLE	BIT(15) /* bypass memory translation */
+#define QMAN_FD_BMT_DISABLE	(0) /* bypass memory translation */
+#define QMAN_FD_SL_DISABLE	(0) /* short lengthe disabled */
+#define QMAN_FD_SL_ENABLE	BIT(14) /* short lengthe enabled */
+
+#define QDMA_FINAL_BIT_DISABLE	(0) /* final bit disable */
+#define QDMA_FINAL_BIT_ENABLE	BIT(31) /* final bit enable */
+
+#define QDMA_FD_SHORT_FORMAT	BIT(11) /* short format */
+#define QDMA_FD_LONG_FORMAT	(0) /* long format */
+#define QDMA_SER_DISABLE	(8) /* no notification */
+#define QDMA_SER_CTX		BIT(8) /* notification by FQD_CTX[fqid] */
+#define QDMA_SER_DEST		(2 << 8) /* notification by destination desc */
+#define QDMA_SER_BOTH		(3 << 8) /* soruce and dest notification */
+#define QDMA_FD_SPF_ENALBE	BIT(30) /* source prefetch enable */
+
+#define QMAN_FD_VA_ENABLE	BIT(14) /* Address used is virtual address */
+#define QMAN_FD_VA_DISABLE	(0)/* Address used is a real address */
+/* Flow Context: 49bit physical address */
+#define QMAN_FD_CBMT_ENABLE	BIT(15)
+#define QMAN_FD_CBMT_DISABLE	(0) /* Flow Context: 64bit virtual address */
+#define QMAN_FD_SC_DISABLE	(0) /* stashing control */
+
+#define QDMA_FL_FMT_SBF		(0x0) /* Single buffer frame */
+#define QDMA_FL_FMT_SGE		(0x2) /* Scatter gather frame */
+#define QDMA_FL_BMT_ENABLE	BIT(15) /* enable bypass memory translation */
+#define QDMA_FL_BMT_DISABLE	(0x0) /* enable bypass memory translation */
+#define QDMA_FL_SL_LONG		(0x0)/* long length */
+#define QDMA_FL_SL_SHORT	(0x1) /* short length */
+#define QDMA_FL_F		(0x1)/* last frame list bit */
+
+/*Description of Frame list table structure*/
+struct dpaa2_qdma_chan {
+	struct dpaa2_qdma_engine	*qdma;
+	struct virt_dma_chan		vchan;
+	struct virt_dma_desc		vdesc;
+	enum dma_status			status;
+	u32				fqid;
+
+	/* spinlock used by dpaa2 qdma driver */
+	spinlock_t			queue_lock;
+	struct dma_pool			*fd_pool;
+	struct dma_pool			*fl_pool;
+	struct dma_pool			*sdd_pool;
+
+	struct list_head		comp_used;
+	struct list_head		comp_free;
+
+};
+
+struct dpaa2_qdma_comp {
+	dma_addr_t		fd_bus_addr;
+	dma_addr_t		fl_bus_addr;
+	dma_addr_t		desc_bus_addr;
+	struct dpaa2_fd		*fd_virt_addr;
+	struct dpaa2_fl_entry	*fl_virt_addr;
+	struct dpaa2_qdma_sd_d	*desc_virt_addr;
+	struct dpaa2_qdma_chan	*qchan;
+	struct virt_dma_desc	vdesc;
+	struct list_head	list;
+};
+
+struct dpaa2_qdma_engine {
+	struct dma_device	dma_dev;
+	u32			n_chans;
+	struct dpaa2_qdma_chan	chans[NUM_CH];
+	int			qdma_wrtype_fixup;
+	int			desc_allocated;
+
+	struct dpaa2_qdma_priv *priv;
+};
+
+/*
+ * dpaa2_qdma_priv - driver private data
+ */
+struct dpaa2_qdma_priv {
+	int dpqdma_id;
+
+	struct iommu_domain	*iommu_domain;
+	struct dpdmai_attr	dpdmai_attr;
+	struct device		*dev;
+	struct fsl_mc_io	*mc_io;
+	struct fsl_mc_device	*dpdmai_dev;
+	u8			num_pairs;
+
+	struct dpaa2_qdma_engine	*dpaa2_qdma;
+	struct dpaa2_qdma_priv_per_prio	*ppriv;
+
+	struct dpdmai_rx_queue_attr rx_queue_attr[DPDMAI_PRIO_NUM];
+	u32 tx_fqid[DPDMAI_PRIO_NUM];
+};
+
+struct dpaa2_qdma_priv_per_prio {
+	int req_fqid;
+	int rsp_fqid;
+	int prio;
+
+	struct dpaa2_io_store *store;
+	struct dpaa2_io_notification_ctx nctx;
+
+	struct dpaa2_qdma_priv *priv;
+};
+
+static struct soc_device_attribute soc_fixup_tuning[] = {
+	{ .family = "QorIQ LX2160A"},
+	{ },
+};
+
+/* FD pool size: one FD + 3 Frame list + 2 source/destination descriptor */
+#define FD_POOL_SIZE (sizeof(struct dpaa2_fd) + \
+		sizeof(struct dpaa2_fl_entry) * 3 + \
+		sizeof(struct dpaa2_qdma_sd_d) * 2)
+
+static void dpaa2_dpdmai_free_channels(struct dpaa2_qdma_engine *dpaa2_qdma);
+static void dpaa2_dpdmai_free_comp(struct dpaa2_qdma_chan *qchan,
+				   struct list_head *head);
+#endif /* __DPAA2_QDMA_H */